{"id":"https://openalex.org/W4372263496","doi":"https://doi.org/10.1109/icassp49357.2023.10095966","title":"Modular Conformer Training for Flexible End-to-End ASR","display_name":"Modular Conformer Training for Flexible End-to-End ASR","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263496","doi":"https://doi.org/10.1109/icassp49357.2023.10095966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095966","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068291585","display_name":"Brian Farris","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Farris","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039108749","display_name":"Pedro J. Garc\u00eda\u2010Moreno","orcid":"https://orcid.org/0000-0002-9793-1826"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759951114654541},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7433404922485352},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5754722356796265},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5611191987991333},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5544549226760864},{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.4866252839565277},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4740222096443176},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4560910761356354},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.428540974855423},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.41832977533340454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4032347500324249},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33254683017730713},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15103256702423096},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08119362592697144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759951114654541},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7433404922485352},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5754722356796265},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5611191987991333},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5544549226760864},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.4866252839565277},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4740222096443176},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4560910761356354},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.428540974855423},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.41832977533340454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032347500324249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33254683017730713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15103256702423096},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08119362592697144},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095966","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1508165687","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2160815625","https://openalex.org/W2531409750","https://openalex.org/W2963211188","https://openalex.org/W2963414781","https://openalex.org/W2975381464","https://openalex.org/W2995181338","https://openalex.org/W3092122846","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3125815078","https://openalex.org/W3163203022","https://openalex.org/W3189164341","https://openalex.org/W3194334755","https://openalex.org/W3201225328","https://openalex.org/W3211278025","https://openalex.org/W4223988178","https://openalex.org/W4225307083","https://openalex.org/W4385245566","https://openalex.org/W6629717138","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6738045163","https://openalex.org/W6739901393","https://openalex.org/W6747398299","https://openalex.org/W6768080748","https://openalex.org/W6784400248","https://openalex.org/W6784614252","https://openalex.org/W6790121257"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W2052399476","https://openalex.org/W2810163160","https://openalex.org/W3083970380","https://openalex.org/W2037964119","https://openalex.org/W4220905048","https://openalex.org/W4385077663","https://openalex.org/W838464343"],"abstract_inverted_index":{"The":[0],"state-of-the-art":[1],"conformer":[2],"used":[3],"in":[4,15],"automatic":[5],"speech":[6],"recognition":[7],"combines":[8],"feed-forward,":[9],"convolution":[10],"and":[11,33,57,68,92,112],"multi-headed":[12],"self-attention":[13],"layers":[14,121],"a":[16,24,88,105],"single":[17],"model":[18,48,86,91,128,147],"that":[19,117],"is":[20,31],"trained":[21],"end-to-end":[22,29],"with":[23,46,104],"decoder":[25],"network.":[26],"While":[27],"this":[28,63],"training":[30,107,124],"simple":[32],"beneficial":[34],"for":[35,130],"word":[36,54],"error":[37,55],"rate,":[38],"it":[39],"restricts":[40],"the":[41,47,84,110,119,123,126,131,142,145],"ability":[42],"to":[43,61],"perform":[44],"inference":[45],"at":[49,98],"different":[50],"operating":[51],"points":[52],"of":[53,125,144],"rate":[56],"latency.":[58],"Existing":[59],"approaches":[60],"overcome":[62],"limitation":[64],"include":[65],"cascaded":[66],"encoders":[67],"variable":[69],"attention":[70,93,120,138],"context":[71],"models.":[72],"We":[73,101,115],"propose":[74],"an":[75],"alternative":[76],"approach,":[77],"called":[78],"Modular":[79],"Conformer":[80,85],"training,":[81],"which":[82,95],"splits":[83],"into":[87],"backbone":[89,127,146],"convolutional":[90],"submodels,":[94,139],"are":[96],"added":[97],"each":[99],"layer.":[100],"conduct":[102],"experiments":[103],"few":[106],"techniques":[108],"on":[109],"Librispeech":[111],"Librilight":[113],"corpus.":[114],"show":[116],"dropping-out":[118],"during":[122],"allows":[129],"largest":[132],"WER":[133,143],"improvements":[134],"upon":[135],"adding":[136],"fine-tuned":[137],"without":[140],"impacting":[141],"itself.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}